- 🔭 I’m currently working on speech synthesis (TTS) for game scenarios, focusing on controllable emotional TTS, audio-visual joint generation, and MIDI-based singing voice synthesis.
- 🌱 I’m currently learning multi-modal large language models, reinforcement learning for generation tasks (DPO/GRPO), advanced speech tokenization techniques, and exploring AI Agents for daily life integration.
- 👯 I’m looking to collaborate on projects related to speech/audio generation, multi-modal AI, and creative applications of AIGC in gaming or entertainment.
- 🤔 I’m looking for help with efficient data cleaning pipelines, scaling up model training, and exploring novel evaluation metrics for generative models.
- 💬 Ask me about speech synthesis, controllable TTS, audio-visual generation, AI Agents or anything related to AI and technology.
- 📫 How to reach me: [email protected]
- 😄 Pronouns: He/Him
